AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics

Yuzhi Huang, Jie Wu, Weijue Bu, Ziyi Xiong, Gaoyang Jiang, Ye Li, Kangye Ji, Shuzhao Xie, Yue Huang, Chenglei Wu, Jingyan Jiang, Zhi Wang

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CSTG (ablation)RoboStream-235B · RLBench long-horizon averagesuccess rate (%): 14.5 -> 90.5Improved
add STF-Tokens on top of CSTG (ablation)RoboStream-235B · RLBench long-horizon averagesuccess rate (%): 79.5 -> 90.5Improved
add STF-Tokens without CSTG (ablation)RoboStream-235B · RLBench long-horizon averagesuccess rate (%): 12.0 -> 14.5Improved
add CSTG (ablation)RoboStream-8B · RLBench long-horizon averagesuccess rate (%): 12.5 -> 58.0Improved
add CSTG (ablation)RoboStream-32B · RLBench long-horizon averagesuccess rate (%): 8.5 -> 82.5Improved
add STF-Tokens on top of CSTG (ablation)RoboStream-8B · RLBench long-horizon averagesuccess rate (%): 45.5 -> 58.0Improved
add STF-Tokens on top of CSTG (ablation)RoboStream-32B · RLBench long-horizon averagesuccess rate (%): 69.0 -> 82.5Improved
scale VLM backbone from 8B to 235BRoboStream · RLBench long-horizon averagesuccess rate (%): 58.0 -> 90.5Improved
use RoboStream-8B instead of SoFarSoFar · RLBench long-horizon averagesuccess rate (%): 28.0 -> 58.0Improved
use RoboStream-8B instead of SoFar (zero-shot)SoFar · SIMPLER WidowX+Bridge averagesuccess rate (%): 58.3 -> 74.8Improved
use RoboStream-32B instead of SoFar-32BSoFar-32B · 6-DoF SpatialBench totalaccuracy (%): 45.3 -> 48.9Improved
use RoboStream-32B instead of SoFar-32BSoFar-32B · Open6DOR V2 6-DoFsuccess rate (%): 48.4 -> 52.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy